Semantic Segmentation On Coco 1
評価指標
mIoU
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | mIoU | Paper Title | Repository |
|---|---|---|---|
| MaskFormer (Swin-L, single-scale) | 64.8 | Masked-attention Mask Transformer for Universal Image Segmentation | |
| Mask2Former (Swin-L, single-scale) | 67.4 | Masked-attention Mask Transformer for Universal Image Segmentation | |
| OneFormer (InternImage-H, emb_dim=1024, single-scale) | 68.8 | OneFormer: One Transformer to Rule Universal Image Segmentation | |
| SegCLIP | 26.5 | SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation | |
| HyperSeg | 77.2 | HyperSeg: Towards Universal Visual Segmentation with Large Language Model | |
| OneFormer (Swin-L, single-scale) | 67.4 | OneFormer: One Transformer to Rule Universal Image Segmentation | |
| OneFormer (DiNAT-L, single-scale) | 68.1 | OneFormer: One Transformer to Rule Universal Image Segmentation |
0 of 7 row(s) selected.